Process control system and operation method thereof

Abstract

The process control system of an embodiment of the present invention includes: a first system for generating thickness information of an internal defect layer contained in a carbon steel product; and a second system for receiving the thickness information of the internal defect layer from the first system via a network, and using the thickness information of the internal defect layer to control an etching process, wherein the etching process is used to remove at least a portion of the internal defect layer from the carbon steel product, the first system providing the second system with a computing module required for the second system to control the etching process, and the second system providing the first system with information required for the first system to update the computing module.

Description

Technical Field

[0001] The present invention relates to a process control system and an operating method thereof, which are used to control a process of removing an internal defect layer included in a carbon steel product. Background Art

[0002] The surface of automobile bearings, etc. produced using carbon steel products may be subjected to continuous and repeated loads. Therefore, carbon steel products used in the production of bearings, etc. require strict surface quality.

[0003] An internal defect layer or the like included in a carbon steel product requires strict management of its thickness, and the internal defect layer can be removed by an etching process or the like. The etching process may be a process of removing the internal defect layer by bringing an etching solution into contact with the carbon steel product.

[0004] This prior art can be easily understood by referring to Korean Patent Publication No. 10-2019-0124019. Summary of the invention

[0005] Technical issues

[0006] One of the technical problems to be solved by the technical idea of ​​the present invention is to provide a process control system and an operating method thereof, which control the etching process according to the thickness of the internal defect layer contained in the carbon steel product, thereby improving the efficiency and productivity of the etching process.

[0007] Technical Solution

[0008] A process control system according to an embodiment of the present invention comprises: a first system for generating thickness information of an internal defect layer contained in a carbon steel product; and a second system for receiving the thickness information of the internal defect layer from the first system via a network, and using the thickness information of the internal defect layer to control an etching process, wherein the etching process is used to remove at least a portion of the internal defect layer from the carbon steel product, the first system providing the second system with a computing module required for the second system to control the etching process, and the second system providing the first system with information required for the first system to update the computing module.

[0009] A process control system according to an embodiment of the present invention comprises: a storage device for storing control data required for controlling an etching device, wherein the etching device is used to remove at least a portion of an internal defect layer contained in a carbon steel product; and a processor for controlling the etching device based on the control data, wherein the carbon steel product comprises a first region and a second region different from the first region, the thickness of the internal defect layer contained in the first region and the thickness of the internal defect layer contained in the second region are different from each other, and the control data comprises a first conveying speed for the first region to pass through the etching device and a second conveying speed for the second region to pass through the etching device, and the first conveying speed and the second conveying speed are different from each other.

[0010] A process control system according to an embodiment of the present invention includes: a storage device for storing a calculation module, wherein the calculation module is used to generate thickness information of an internal defect layer contained in the carbon steel product based on at least one of the composition, cooling rate, phase fraction and temperature of the carbon steel product; a communication unit connected to a network; and a processor, wherein the processor is used to transmit at least one of the thickness information of the internal defect layer and control data for controlling an etching process to an external server through the communication unit, wherein the external server is used to control the etching process for removing at least a portion of the internal defect layer.

[0011] Effects of the Invention

[0012] According to one embodiment of the present invention, a process control system and an operating method thereof can be provided, wherein the process control system and the operating method thereof control the etching process based on optimal control data during the period when each area defined in the length direction of the carbon steel product is in contact with the etching solution, thereby being able to improve the productivity and efficiency of the etching process.

[0013] In addition, according to one embodiment of the present invention, by measuring the thickness of the remaining internal defect layer contained in the pickled carbon steel product that has completed the etching process, and using the measured thickness of the remaining internal defect layer, a calculation module for generating control data for controlling the etching process is learned, so that the etching process can be performed based on the optimal control data.

[0014] The various beneficial advantages and effects of the present invention are not limited to the above contents, and the advantages and effects of the present invention should be more easily understood in the process of describing the specific embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a diagram for explaining a process for preparing a hot-rolled steel sheet according to an embodiment of the present invention.

[0016] Figure 2 This is a diagram simply showing a hot-rolled steel sheet according to an embodiment of the present invention.

[0017] Figure 3 is a block diagram showing a process control system according to an embodiment of the present invention.

[0018] Figure 4 It is a block diagram simply showing a process control system according to an embodiment of the present invention.

[0019] Figure 5 It is a diagram for explaining an initial learning method of a calculation module included in a process control system according to an embodiment of the present invention.

[0020] Figure 6 It is a diagram for explaining a learning model included in a process control system according to an embodiment of the present invention.

[0021] Figure 7 It is a diagram for explaining an operating method of a process control system according to an embodiment of the present invention.

[0022] Figure 8 It is a flowchart for explaining an operating method of a process control system according to an embodiment of the present invention.

[0023] Fig. 9 It is a block diagram simply showing a process control system according to an embodiment of the present invention.

[0024] Fig.10 It is a diagram for explaining an operating method of a process control system according to an embodiment of the present invention.

[0025] Fig.11 It is a diagram for explaining a learning method of a calculation module included in a process control system according to an embodiment of the present invention.

[0026] Fig.12 It is a diagram for explaining an etching process according to an embodiment of the present invention.

[0027] Fig.13 The diagram is provided to illustrate an etching process according to an embodiment of the present invention.

[0028] Fig.14 It is a diagram for explaining an initial learning method of a calculation module included in a process control system according to an embodiment of the present invention.

[0029] Fig.15 It is a diagram for explaining a learning method of a calculation module included in a process control system according to an embodiment of the present invention.

[0030] Fig.16 It is a flowchart for explaining an operating method of a process control system according to an embodiment of the present invention.

[0031] Fig.17It is a diagram for explaining an operating method of a process control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In this specification, carbon steel products are alloy products of iron and carbon, which contain 0.01% to 2.0% carbon, and may typically include hot-rolled products, thick plate products, and wire products. For example, the hot-rolled product may be a hot-rolled coil or a hot-rolled steel plate made by hot-rolling a slab and coiling it in a coil, and may have a thickness of 1 mm to 25 mm. The thick plate product may be a product made by hot-rolling a slab and forming it into a plate, and may have a thickness of 4 mm to 200 mm. The wire product may be a coiled product with a circular cross-section made by pass-rolling a steel billet in a hot state, and may have a cross-sectional diameter of 3 mm to 100 mm.

[0033] The process control system of the present invention can produce carbon steel products after pickling treatment (hereinafter referred to as "pickled carbon steel products") by controlling the conveying speed of the carbon steel products during the etching process of the carbon steel products, thereby improving the surface quality of the carbon steel products.

[0034] The technical concept of the present invention is described below with a focus on a hot-rolled steel sheet or a hot-rolled coil in which the hot-rolled steel sheet is coiled. However, the technical concept of the present invention is not limited to the hot-rolled steel sheet or the hot-rolled coil, and the technical concept of the present invention can be applied to all carbon steel products within the scope that can be easily understood by those skilled in the art.

[0035] Hereinafter, the preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The same reference numerals are used for the same structural elements in the drawings, and repeated descriptions of the same structural elements are omitted.

[0036] Figure 1 It is a diagram for explaining a process for preparing a hot-rolled steel sheet according to an embodiment of the present invention.

[0037] Figure 1 This is a diagram showing a simple hot-rolled steel sheet production device, which is used to produce hot-rolled steel sheets and produce hot-rolled coils by cooling and coiling the hot-rolled steel sheets. Figure 1 , a hot rolling process can be performed, in which a slab heated in a heating furnace is rolled to a specified thickness using a roughing mill and a finishing mill (or a final rolling mill). The hot-rolled steel plate (strip) produced by the hot rolling process can be moved to a cooling zone, i.e., a Run Out Table (ROT) cooling table. The hot-rolled steel plate can be cooled by cooling water sprayed from the ROT cooling table, and the cooling temperature and cooling time can be determined according to the quality required for the hot-rolled steel plate.

[0038] After cooling, the hot rolled steel sheet can be coiled in a coiler for easy storage and / or transportation. The hot rolled coil (HC) formed by coiling the hot rolled steel sheet in a coil is placed in a yard, air cooled and shipped, and then an etching process for removing the internal defect layer contained in the hot rolled steel sheet can be performed. In one embodiment, referring to Figure 1 The hot rolled steel plate preparation process and the etching process for removing the internal defect layer of the hot rolled steel plate can be performed by different entities. In addition, in one embodiment, the hot rolled steel plate preparation process and the etching process for removing the internal defect layer of the hot rolled steel plate can also be performed by the same entity.

[0039] Figure 2 This is a diagram simply showing a hot-rolled steel sheet according to an embodiment of the present invention.

[0040] Reference Figure 2 The hot-rolled steel sheet can be divided into a plurality of regions along the length direction (X-axis direction). For example, the hot-rolled steel sheet may include region A, region B, and region C, etc., which are sequentially arranged along the length direction. Figure 2 In one embodiment shown in , region A may be the region that is first coiled in the hot rolled steel sheet, and region C may be the region that is last coiled. Region B may be a region located between region A and region C in the length direction.

[0041] In one embodiment, the hot rolled steel sheet may include surface defects. For example, the surface defects may include at least one of an oxide scale and an internal defect layer. The oxide scale is generated during the rolling process and may exist on the surface of the material. The internal defect layer may be contained below the surface of the material, i.e., inside the material, and the internal defect may be defined as meaning an internal oxide layer and / or a decarburized layer. The internal oxide layer may be generated in the process in which components such as chromium (Cr), manganese (Mn), silicon (Si), zinc (Zn), magnesium (Mg), and aluminum (Al) having a higher affinity for oxygen than iron (Fe) cause oxidation inside the parent material. The decarburized layer may be generated in the process in which carbon in the steel combines with oxygen in the atmosphere and the oxide scale and is discharged into the atmosphere in the form of gas. The thickness of the internal defect may vary depending on the composition of the hot rolled steel sheet, the temperature when the hot rolled steel sheet is coiled into a hot rolled coil (HC), the cooling time after coiling, the width, thickness, and length of the hot rolled steel sheet, etc. Internal defects such as the internal defect layer may become an important factor in reducing the durability of products produced using the hot rolled steel sheet.

[0042] As an example, the temperature of the coiled hot-rolled coil (HC) may be about 500 to 700°C, and the coiled hot-rolled coil (HC) may be cooled by air cooling in a state exposed to the air. In the coiled hot-rolled coil (HC), the A region and the C region exposed to the outside can be cooled relatively quickly, while the unexposed B region is cooled relatively slowly. Therefore, the thickness of the internal defect layer contained in the B region of the hot-rolled steel plate may be greater than the thickness of the internal defect layer contained in the A region and the C region of the hot-rolled steel plate, respectively. Therefore, the thickness of the internal defect layer may deviate depending on the region of the hot-rolled steel plate. As an example, the thickness of the internal defect layer contained in the A region and / or the C region may be less than the specified reference thickness, and the thickness of the internal defect layer contained in the B region may be greater than the reference thickness.

[0043] In addition, the thickness of the internal defect layer may also be different depending on the region in the width direction of the hot-rolled steel sheet. For example, in the width direction, the region adjacent to the edge of the hot-rolled steel sheet may be cooled relatively quickly, and the thickness difference of the internal defect layer at different cooling rates may also occur in the width direction.

[0044] The etching process for removing at least a portion of the internal defect layer may be performed by contacting the hot-rolled steel sheet with an etching solution. As an example, the etching process may be performed by conveying the hot-rolled steel sheet while immersed in the etching solution contained in an etching tank. Alternatively, the etching process may be performed by spraying the etching solution onto the surface of the hot-rolled steel sheet in the etching tank or by brushing the surface of the hot-rolled steel sheet with a brush soaked in the etching solution. The etching process may be at least one of an acid pickling process, a dry etching process, and a wet etching process.

[0045] As an example, in the etching process, the hot-rolled steel sheet can be brought into sufficient contact with the etching solution regardless of the region of the hot-rolled steel sheet to perform the etching process, thereby sufficiently removing the internal defect layer contained in the hot-rolled steel sheet. However, the above method may increase the time of the etching process and / or the etching solution input into the etching process, thereby reducing productivity.

[0046] According to one embodiment of the present invention, the thickness of the internal defect layer contained in the hot-rolled steel plate along the length direction of the hot-rolled steel plate can be calculated and / or measured, and the etching process can be controlled with the best efficiency according to the thickness information of the internal defect layer. Therefore, the time of the etching process can be shortened and the amount of etching solution used can be reduced, thereby improving productivity. In addition, the thickness deviation of the internal defect layer generated by region on the pickled steel plate after the etching process is completed can be reduced.

[0047] Figure 3 is a block diagram showing a process control system according to an embodiment of the present invention.

[0048] According to an embodiment of the present invention, the process control system 1 may include: a first system SYS1 for generating thickness information of an internal defect layer contained in a hot-rolled coil formed by coiling a hot-rolled steel sheet; and a second system SYS2 for controlling an etching process, wherein the etching process is used to remove at least a portion of the internal defect layer in the hot-rolled steel sheet released from the hot-rolled coil using the thickness information of the internal defect layer received from the first system SYS1. In addition, the first system SYS1 may provide the second system SYS2 with a computing module required for the second system SYS2 to control the etching process. In addition, the second system SYS2 may obtain information required by the first system SYS1 to update the computing module and provide it to the first system SYS1. The first system SYS1 and the second system SYS2 may communicate with each other via a network 30.

[0049] Reference Figure 3 The process control system 1 of one embodiment of the present invention can be operated by a first body that performs a hot rolling process and a second body that performs an etching process. In one embodiment, the first body can produce hot-rolled steel sheets and coil the hot-rolled steel sheets to prepare hot-rolled coils, and the second body can receive the hot-rolled coils from the first body and perform an etching process to remove the internal defective layer of the hot-rolled steel sheets. Figure 3 , the first system SYS1 can be operated by the first subject, and the second system SYS2 can be operated by the second subject. However, according to an embodiment, the first system SYS1 and the second system SYS2 can also be operated by the same subject. In this case, the network 30 can be an internal network of the subject that operates both the first system SYS1 and the second system SYS2.

[0050] Reference Figure 3 The first system SYS1 may include a first server 10, and the second system SYS2 may include a second server 20. The first server 10 and the second server 20 may communicate via a network 30, and the second system SYS2 may control an etching device 22 for removing at least a portion of an internal defect layer of a hot-rolled steel plate.

[0051] The network 30 may mean a wired Internet network, a wireless Internet network, or a wireless local area network (WLAN) such as Wi-Fi (wireless fidelity), etc. The wired Internet network or the wireless Internet network may mean an open computer network structure that provides Internet TCP / IP protocol and various services existing in its upper layer, namely HTTP (HyperText Transfer Procotol), Telnet (remote login), FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), SNMP (Simple Network Management Protocol), NFS (Network File Service) and NIS (Network Information Service), etc.

[0052] In one embodiment, the first system SYS1 may generate thickness information of an internal defect layer of a hot-rolled steel plate produced in a hot rolling process. The first system SYS1 may transmit the thickness information of the internal defect layer to the second system SYS2 via the network 30. The second system SYS2 may control the etching process performed by the etching device 22 using the thickness information of the internal defect layer received via the network 30.

[0053] As an example, the first system SYS1 may include a first server 10, and the first server 10 may include a calculation module 11 and a learning model for the calculation module 11 to learn. In one embodiment, the thickness information of the internal defect layer may be generated by the calculation module 11. The first system SYS1 may generate the thickness information by measuring the thickness of the internal defect layer of the hot-rolled steel plate, or by calculating the thickness of the internal defect layer of the hot-rolled steel plate. In one embodiment, the first system SYS1 may calculate the thickness of the internal defect layer using at least one of the composition of the hot-rolled steel plate, the phase fraction of the hot-rolled steel plate, and the temperature of the hot-rolled steel plate, thereby generating the thickness information of the internal defect layer.

[0054] The thickness information of the internal defect layer may include the thickness of the internal defect layer contained in the hot-rolled steel plate in each of a plurality of regions defined in the length direction of the hot-rolled steel plate. Therefore, the thickness information of the internal defect layer may include the thickness distribution of the internal defect layer expressed along the length direction of the hot-rolled steel plate, etc.

[0055] According to another embodiment, information related to the thickness of the internal defect layer may be generated by the calculation module 11. Information related to the thickness of the internal defect layer may mean all forms of information from which the thickness information of the internal defect layer is processed in a manner that the thickness information of the internal defect layer can be extracted. When the first system SYS1 transmits information related to the thickness of the internal defect layer to the second system SYS2 through the network 30, the second system SYS2 may extract the thickness information of the internal defect layer contained in the information related to the thickness of the internal defect layer received through the network 30, or calculate the thickness information of the internal defect layer based on the thickness related information, and control the etching process performed by the etching device 22 using the extracted or calculated thickness information of the internal defect layer.

[0056] The calculation module 21 of the second system SYS2 may generate control data required for controlling the etching device 22. As an example, the calculation module 21 may generate the control data using the thickness information of the internal defect layer received from the first system SYS1. The control data may include at least one of the speed at which the hot-rolled steel sheet is conveyed by the etching device 22 during the etching process, the concentration of the etching solution in contact with the hot-rolled steel sheet in the etching device 22, the composition of the etching solution, the temperature of the etching solution, and whether an accelerator is used.

[0057] The calculation module 21 of the second system SYS2 may be at least one of the calculation modules 11 stored and managed by the first system SYS1 and received by the second system SYS2. The first system SYS1 may provide the module required for controlling the etching device 22 in the calculation module 11 to the second system SYS2. As an example, the first system SYS1 may learn the module required for controlling the etching device 22 using the learning model 12 and then provide the module to the second system SYS2. The first system SYS1 may provide the module to the second system SYS2 using a transmission method through the network 30. Alternatively, the module learned by the first system SYS1 may be provided to the second system SYS2 by an operator directly inputting the module and storing it in the second system SYS2.

[0058] The second system SYS2 may provide the first system SYS1 with information required by the first system SYS1 to update the calculation module 11. As an example, when the etching device 22 completes the etching process of the hot-rolled steel plate to produce the pickled steel plate, the second system SYS2 may provide the first system SYS1 with at least one of the thickness of the remaining internal defect layer in the pickled steel plate and the control data measured in the etching device 22 during the etching process. The first system SYS1 may update the calculation module 11 using at least one of the thickness of the remaining internal defect layer and the control data received from the second system SYS2. As an example, the learning model 12 may use at least one of the thickness of the remaining internal defect layer and the control data to enable the calculation module 11 to learn, thereby updating the calculation module 11.

[0059] After updating the computing modules 11, the first system SYS1 may transmit at least one of the updated computing modules 11 to the second system SYS2 via the network 30. The second system SYS2 may use the computing modules 11 received from the first system SYS1 to update the stored computing modules 21. As an example, the second system SYS2 may overwrite the existing computing modules 21 with the computing modules received from the first system SYS1.

[0060] In one embodiment, the calculation module 11 of the first system SYS1 may be a plurality of calculation modules. The calculation module 11 may include a calculation module for generating thickness information of an internal defect layer contained in a hot-rolled steel plate and a calculation module for generating control data for controlling the etching device 22. The first system SYS1 may transmit the calculation module for generating control data to the second system SYS2.

[0061] The learning model 12 can optimize the calculation module 11. As an example, the learning model 12 may include a plurality of learning models for enabling the plurality of calculation modules to learn. In addition, the learning model 12 may use at least one of the thickness of the remaining internal defect layer and the control data received from the second system SYS2 to enable the calculation module 11 to learn, thereby achieving optimization. In one embodiment, the learning model 12 may enable the calculation module 11 to learn, so that the thickness of the remaining internal defect layer calculated by the calculation module 11 and the thickness of the remaining internal defect layer received from the second system SYS2 are consistent with each other or the difference between the two is below a prescribed reference value.

[0062] The calculation module 11 may be implemented by hardware such as a circuit, or may be implemented by software such as a source code. The calculation module 11 may perform a predetermined calculation using an input value to generate an output value. As an example, the learning model 12 may adjust weights and coefficients in the calculation performed in the calculation module 11 to enable the calculation module 11 to learn.

[0063] According to an embodiment, the second server 20 of the second system SYS2 may further include an additional computing module. The additional computing module may be an additional computing module different from the computing module 21 received from the first system SYS1, which may adjust at least a portion of the control data output by the computing module 21 and input it to the etching device 22. As an example, considering mechanical errors and operation delays existing in the etching device 22, the additional computing module may adjust at least a portion of the control data output by the computing module 21 and input it to the etching device 22. Therefore, when the second server 20 includes the additional computing module, the control data output by the computing module 21 and the control data input to the etching device 22 may be different from each other.

[0064] The additional computing module may adjust the scale unit of the control data or convert the control data into a data format that can be input to the etching device 22, so that the control data output by the computing module 21 can be applied to the etching device 22. According to an embodiment, the computing module 21 may also directly adjust the scale unit and data format of the control data and output it to the etching device 22. In this case, the second server 20 may not include the additional computing module.

[0065] In one embodiment, the calculation module 21 of the second system SYS2 may receive thickness information of the internal defect layer from the first system SYS1. The thickness information may include the thickness of the internal defect layer calculated and / or measured by the first system SYS1. The second system SYS2 may determine control data for controlling the etching device 22 using the thickness information. In one embodiment, the control data may include the conveying speed of the hot-rolled steel sheet conveyed by the etching device 22, the concentration of the etching solution in contact with the hot-rolled steel sheet in the etching device 22, the temperature of the etching solution, the composition of the etching solution, and whether an accelerator is used. The etching device 22 may be automatically controlled by the control data output by the calculation module 21.

[0066] As an example, the control data input to the etching device 22 can optimize the etching process performed on each of the multiple regions defined along the length direction of the hot-rolled steel plate. For example, the conveying speed of the hot-rolled steel plate in the etching process of the partial region near the end of the hot-rolled steel plate and the conveying speed of the hot-rolled steel plate in the etching process of the other partial region away from the end of the hot-rolled steel plate can be different. As an example, the conveying speed of the hot-rolled steel plate in the etching process of the partial region near the end of the hot-rolled steel plate can be faster than the conveying speed of the hot-rolled steel plate in the etching process of the other partial region away from the end of the hot-rolled steel plate. In one embodiment, during the etching process, the oxide scale present on the surface of the hot-rolled steel plate can be removed at the same time.

[0067] In one embodiment, due to mechanical errors in the etching device 22 and signal delays in the process of inputting and outputting control data, the control data output by the calculation module 21 and the control data actually measured in the etching device 22 during the etching process may be inconsistent. If the conveying speed of the hot-rolled steel sheet in the control data input to the etching device 22 is used as an example, the conveying speed of the hot-rolled steel sheet input by the calculation module 21 to the etching device 22 and the actual conveying speed of the hot-rolled steel sheet transported by the etching device 22 may be inconsistent. In addition, the concentration of the etching solution and / or the temperature of the etching solution in the control data input to the etching device 22 may change during the contact between the hot-rolled steel sheet and the etching solution.

[0068] In one embodiment of the present invention, the etching device 22 may be controlled in consideration of mechanical errors and signal delays, etc. As an example, the second system SYS2 may obtain information including the thickness of the remaining internal defect layer in the pickled steel plate after the etching process and control data measured in the etching device 22 during the etching process, so that the mechanical errors and signal delays, etc. may be reflected in the control data. The second system SYS2 may transmit the obtained information to the first system SYS1.

[0069] The learning model 12 of the first system SYS1 can use the information transmitted by the second system SYS2 to enable at least one of the calculation modules 11 to learn. After completing the learning of the calculation module 11, the first system SYS1 can transmit at least one of the calculation modules 11 that has completed learning, such as a calculation module for generating control data for controlling the etching device 22, to the second system SYS2. The second system SYS2 can update the stored calculation module 21 using the calculation module received from the first system SYS1. Therefore, the calculation module 21 of the second system SYS2 can generate control data in consideration of mechanical errors and signal delays, and can control the etching device 22 more accurately.

[0070] According to an embodiment, the second system SYS2 may also include a learning model. The learning model included in the second system SYS2 may enable the computing module 21 included in the second system SYS2 to learn in a manner similar to the learning model 12 included in the first system SYS1. Fig.14 and Fig.15 Provide explanation.

[0071] In addition, the thickness of the internal defect layer contained in the hot-rolled steel sheet can be directly calculated by the second system SYS2, and the etching process can be performed using the thickness. At this time, the second system SYS2 can receive the information required to calculate the thickness of the internal defect layer from the first system SYS1. As an example, the first system SYS1 can collect information such as the cooling rate of the hot-rolled steel sheet, the composition of the hot-rolled steel sheet, and the oxygen partial pressure of the surrounding area during the cooling of the hot-rolled steel sheet, and transmit this information to the second system SYS2. The calculation module 21 of the second system SYS2 can use the variables received from the first system SYS1 to predict the thickness of the internal defect layer contained in the hot-rolled steel sheet and control the etching device 22.

[0072] In one embodiment, as described above, the calculated thickness of the internal defect layer can be used to adjust the conveying speed of the hot-rolled steel sheet during the etching process. As an example, the hot-rolled steel sheet can be conveyed at a first conveying speed during the period when the first region where the thickness of the internal defect layer is predicted to be relatively small contacts the etching solution. In addition, the hot-rolled steel sheet can be conveyed at a second conveying speed slower than the first conveying speed during the period when the second region where the thickness of the internal defect layer is predicted to be relatively large contacts the etching solution.

[0073] In one embodiment of the present invention, the following operations can be implemented in two different systems SYS1 and SYS2: these operations are operations for collecting information for predicting the internal defect layer of the hot-rolled steel plate, operations for calculating the internal defect layer, operations for generating control data for controlling the etching device 22 based on the calculated internal defect layer, and operations for re-learning the calculation modules 11 and 21 using the control data collected during the etching process performed by the etching device 22. As an example, these operations can be appropriately distributed and executed in the first system SYS1 and the second system SYS2 as needed. As an example, the operations can be allocated to the first system SYS1 and the second system SYS2 according to the performance of the first system SYS1 and the second system SYS2, so as to efficiently manage the load of the systems SYS1 and SYS2 and effectively operate the entire system 1.

[0074] For example, when the performance of the first system SYS1 is much better than that of the second system SYS2, the first system SYS1 may process most of the operations, and the second system SYS2 may receive the control data generated by the first system SYS1 to control the etching device 22. When the performance of the first system SYS1 and the second system SYS2 are similar, the first system SYS1 may generate thickness information indicating the thickness of the internal defect layer contained in the hot-rolled steel plate, and the second system SYS2 may generate control data using the thickness information of the internal defect layer. On the contrary, when the performance of the second system SYS2 is much better than that of the first system SYS1, the first system SYS1 may collect the information of the hot-rolled steel plate required for calculating the thickness of the internal defect layer and transmit it to the second system SYS2, and the second system SYS2 may calculate the thickness of the internal defect layer and generate control data to control the etching device 22.

[0075] In order to predict the thickness of the internal defect layer, the information of the hot-rolled steel plate received by the second system SYS2 from the first system SYS1 may include information related to the phase fraction of the hot-rolled steel plate, information related to the temperature of the hot-rolled steel plate, and information related to the composition of the hot-rolled steel plate. Information related to the phase fraction may mean all forms of information after the phase fraction information is processed in a manner that can extract the phase fraction information, information related to the temperature of the hot-rolled steel plate may mean all forms of information after the temperature information is processed in a manner that can extract the temperature information, and information related to the composition of the hot-rolled steel plate may mean all forms of information after the composition information is processed in a manner that can extract the composition information. Therefore, the second system SYS2 can use the information received from the first system SYS1 to first calculate the phase fraction, temperature, and composition of the hot-rolled steel plate, and then use these data to predict the thickness of the internal defect layer contained in the hot-rolled steel plate.

[0076] Figure 4 It is a block diagram simply showing a process control system according to an embodiment of the present invention.

[0077] Reference Figure 4 The process control system 40 of one embodiment of the present invention may include a first server 41 and a hot-rolled steel plate production device 45, etc. The first server 41 may control and manage the hot-rolled steel plate production device 45. The hot-rolled steel plate production device 45 may be a device for rolling a slab heated in a heating furnace to produce a hot-rolled steel plate, and for cooling and coiling the hot-rolled steel plate.

[0078] The first server 41 may include a communication unit 42, a storage device 43, a processor 44, etc. The communication unit 42 may connect the first server 41 to a network so that communication is possible. The storage device 43 may store data required for the operation of the first server 41 and the management of the hot-rolled steel sheet production device 45, etc. The processor 44 may control the communication unit 42, the storage device 43, the hot-rolled steel sheet production device 45, etc.

[0079] As an example, the storage device 43 may store a calculation module for performing a prescribed calculation. In one embodiment, the calculation module may be linked with the hot-rolled steel plate production device 45, and use the information obtained from the hot-rolled steel plate production device 45 to generate the thickness information of the internal defect layer contained in the hot-rolled steel plate. In addition, the calculation module may generate control data required for controlling the etching device through an external system connected through the communication unit 42 and a network. The etching device may be a device for removing at least a portion of the internal defect layer contained in the hot-rolled steel plate produced by the hot-rolled steel plate production device 45.

[0080] For example, the control data may include the conveying speed of the hot-rolled steel plate conveyed by the etching device, the temperature and concentration of the etching solution in contact with the hot-rolled steel plate in the etching device, the composition and whether the accelerator is used, etc. As an example, in the thickness information of the internal defect layer generated by the calculation module, the first area of ​​the hot-rolled steel plate may have an internal defect layer of a first thickness, and the second area may have an internal defect layer of a second thickness different from the first thickness. The control data may include a first conveying speed for conveying the hot-rolled steel plate in the etching process of the first area and a second conveying speed for conveying the hot-rolled steel plate in the etching process of the second area, and the first conveying speed and the second conveying speed may be different from each other. As an example, when the first thickness is greater than the second thickness, the first conveying speed may be slower than the second conveying speed. Therefore, it is possible to perform a sufficient etching process on an area with a relatively large thickness.

[0081] In one embodiment, the storage device 43 may be used to store a learning model required for the computing module to learn. The learning model may be executed by the processor 44, and the processor 44 may optimize the computing module by executing the learning model.

[0082] The processor 44 can be implemented by a CPU, an AP, a SoC, etc., and can control the storage device 43, the communication unit 42, the hot-rolled steel plate production device 45, etc. As an example, the processor 44 can transmit at least one of the thickness information of the internal defect layer generated by the calculation module stored in the storage device 43 and the control data required by the external system to control the etching device to the external system.

[0083] When the processor 44 transmits the thickness information of the internal defect layer to the external system, the external system can directly generate control data for controlling the etching device based on the thickness information of the internal defect layer. At this time, the processor 44 can extract the calculation module for generating control data using the thickness information of the internal defect layer from the storage device 43 and transmit it to the external system.

[0084] In addition, when the processor 44 transmits control data to the external system, the external system can control the etching device using the received control data. If necessary, additional operations such as changing the format of the control data can be performed in the external system. At this time, the processor 44 may not transmit the calculation module that generates the control data using the thickness information of the internal defect layer to the external system.

[0085] In one embodiment, the calculation module stored in the storage device 43 may include a first module for calculating the phase fraction before the hot rolled steel sheet production device 45 coils the hot rolled steel sheet. The first module may calculate the phase fraction based on the process conditions of the hot rolled steel sheet, such as at least one of the cooling rate of the hot rolled steel sheet, the composition of the hot rolled steel sheet, and the initial temperature of the hot rolled steel sheet. The learning model of the storage device 43 may compare the phase fraction actually measured in the hot rolled steel sheet with the phase fraction predicted by the first module through calculation, and enable the first module to learn.

[0086] In one embodiment, the calculation module stored in the storage device 43 may further include a second module for calculating the temperature change of the hot-rolled steel sheet. The second module may predict the temperature change using at least one of the phase fraction calculated by the first module, the time elapsed after the hot-rolled steel sheet is coiled, and the composition of the hot-rolled steel sheet. The learning model may compare the temperature change calculated by the second module with the temperature change actually measured in the hot-rolled steel sheet, and enable the second module to learn.

[0087] In one embodiment, the calculation module stored in the storage device 43 may further include a third module for calculating the thickness of the internal defect layer contained in the hot-rolled steel plate. As an example, the third module may calculate the thickness of the internal defect layer using at least one of the temperature change calculated by the second module, the composition of the hot-rolled steel plate, and the oxygen partial pressure around the hot-rolled steel plate. The learning model may compare the thickness of the internal defect layer predicted by the third module through calculation with the thickness of the internal defect layer actually measured from the hot-rolled steel plate, and enable the third module to learn.

[0088] As an example, the third module may calculate the thickness of the internal defect layer in each of a plurality of regions defined along the length direction of the hot-rolled steel sheet. The thicknesses of the internal defect layer calculated in at least a portion of the plurality of regions may be different from each other.

[0089] In one embodiment, the calculation module stored in the storage device 43 may further include a fourth module for calculating the thickness of the internal defect layer removed in the etching process of removing at least a portion of the internal defect layer. The fourth module may calculate the thickness of the internal defect layer removed in the etching process based on control data input into the etching device for controlling the etching device performing the etching process.

[0090] The learning model may compare the thickness of the remaining internal defect layer contained in the pickled steel plate after the etching process is completed with the thickness of the internal defect layer predicted by the fourth module through calculation, and enable the fourth module to learn. As an example, the learning model may compare the difference between the thickness of the internal defect layer calculated by the third module and the thickness of the internal defect layer calculated by the fourth module with the thickness of the remaining internal defect layer contained in the pickled steel plate. In order to enable the fourth module to learn, the first server 41 may receive the thickness of the remaining internal defect layer measured in the pickled steel plate by the external system controlling the etching device.

[0091] In one embodiment, the calculation module stored in the storage device 43 may further include a fifth module for generating control data required by the external system to control the etching device. The control data generated by the fifth module may include at least one of the speed at which the hot-rolled steel sheet is conveyed by the etching device, the concentration of the etching solution in contact with the hot-rolled steel sheet in the etching device, the composition of the etching solution, the temperature of the etching solution, and whether an accelerator is used.

[0092] The first server 41 may receive control data from an external system for controlling the etching device so that the learning model enables the fifth module to learn. The control data received by the first server 41 from the external system may be control data actually measured by the external system from the etching device during the etching process. The learning model may compare the thickness of the internal defect layer calculated by the fourth module using the control data received from the external system and the thickness of the remaining internal defect layer actually measured from the pickled steel plate, and enable the fifth module to learn.

[0093] Figure 5 It is a diagram for explaining an initial learning method of a calculation module included in a process control system according to an embodiment of the present invention.

[0094] Reference Figure 5 , the thickness control system 100 of the internal defect layer of the hot-rolled steel plate may include a calculation module 110 and a learning model 120. As an example, the calculation module 110 may include a thickness information generation module 111 and a control data generation module 112. In one embodiment, the calculation module 110 may include first to fifth modules M1-M5, the thickness information generation module 111 may include first to third modules M1-M3, and the control data generation module 112 may include a fourth module M4 and a fifth module M5. The first to fifth modules M1-M5 may be implemented by hardware such as circuits or by software such as source code.

[0095] For example, when the first to fifth modules M1 to M5 are implemented by software such as source code, the first to fifth modules M1 to M5 may perform calculations to calculate output data using input data. The calculations of each of the first to fifth modules M1 to M5 may be determined and optimized by the learning model 120 .

[0096] The learning model 120 may include first to fourth learning models LM1~LM4 and a feedback learning model LMT. The first learning model LM1 may be a model for initial learning of the first module M1, and the second learning model LM2 may be a model for initial learning of the second module M2. Similarly, the third learning model LM3 may be a model for initial learning of the third module M3, and the fourth learning model LM4 may be a model for initial learning of the fourth module M4. The feedback learning model LMT may be a model for learning at least one of the first to fifth modules M1~M5 after the etching process is completed. In one embodiment, the feedback learning model LMT may also enable the first to fifth modules M1~M5 to learn simultaneously.

[0097] The learning model 120 may use a bias correction method or reinforcement learning to enable the first to fifth modules M1 to M5 to learn. When the bias correction method is used, the learning model 120 may enable the first to fifth modules M1 to M5 to learn by correcting the error between the measurement value input from the outside and the calculated value output from the module. When the learning model 120 uses reinforcement learning, the learning model 120 may be a DNN (deep neural network), but is not necessarily limited to the example described above.

[0098] For an embodiment in which the learning model 120 uses reinforcement learning to enable each module to learn, reference will be made later. Figure 6 Next, refer to Figure 5 , the initial learning method of the process control system 100 is described in detail.

[0099] In one embodiment, the first module M1 may calculate the phase fraction before the hot rolled steel sheet is coiled. The first learning model LM1 may receive the first process condition CD1 and the first phase fraction value EPF. The first phase fraction value EPF may include the phase change fraction or phase amount actually measured under the first process condition CD1. The first process condition CD1 may include the cooling rate of the hot rolled steel sheet, the temperature of the hot rolled steel sheet, and the composition of the hot rolled steel sheet.

[0100] The first learning model LM1 can input the first process condition CD1 to the first module M1. The first module M1 can calculate the phase fraction of the hot-rolled steel sheet using the first process condition CD1 to obtain a second phase fraction value PPF. The second phase fraction value PPF output by the first module M1 can be transmitted to the first learning model LM1.

[0101] The first learning model LM1 can compare the first phase fraction value EPF and the second phase fraction value PPF, and make the first module M1 learn. As an example, when the first phase fraction value EPF and the second phase fraction value PPF are inconsistent, the first learning model LM1 can adjust the weighted value and coefficient of the first calculation, which is the calculation of the first module M1 by receiving the first process condition CD1 and calculating the phase fraction. The first learning model LM1 can adjust the weighted value and coefficient of the first calculation of the first module M1 to make the first phase fraction value EPF and the second phase fraction value PPF consistent or to make the difference between the first phase fraction value EPF and the second phase fraction value PPF reach a specified value or less.

[0102] The second learning model LM2 may receive the second process condition CD2, the environmental condition FV representing the surrounding environment, and the first temperature value ET measured from the hot-rolled steel sheet. The second process condition CD2 may include the time point at which the temperature of the hot-rolled steel sheet after coiling is measured and the composition of the hot-rolled steel sheet. The environmental condition FV may include a value of the surrounding environment that affects the cooling rate of the hot-rolled steel sheet after coiling. For example, when the surrounding environment is air, the value of the environmental condition FV may be "1", when the surrounding environment is wind, the value of the environmental condition FV may be "2", and when the surrounding environment is water, the value of the environmental condition FV may be "3". The first temperature value ET may include the actual measured value of the temperature of the hot-rolled coil.

[0103] The second module M2 may receive the second process condition CD2 and the environmental condition FV from the second learning model LM2. As an example, the second module M2 may calculate the temperature of the hot-rolled steel plate using the second process condition CD2 and the environmental condition FV, and may output a second temperature value PT after calculating the temperature of the hot-rolled steel plate. The second temperature value PT may include a value calculated based on the time after coiling for the temperature of each region defined in the length direction of the hot-rolled steel plate, etc. The second module M2 may output the second temperature value PT to the second learning model LM2.

[0104] The second learning model LM2 can compare the first temperature value ET and the second temperature value PT and make the second module M2 learn. For example, when the first temperature value ET and the second temperature value PT are inconsistent or the difference between the first temperature value ET and the second temperature value PT is greater than a specified value, the second learning model LM2 can adjust the weighting value and coefficient of the second calculation of the second temperature value PT in the second module M2. The second learning model LM2 can make the second module M2 learn so that the first temperature value ET and the second temperature value PT are consistent or the difference between the first temperature value ET and the second temperature value PT is less than a specified value.

[0105] The third learning model LM3 may receive the composition ING of the hot-rolled steel plate, the oxygen partial pressure OPP around the hot-rolled steel plate, the output value of the second module M2, i.e., the second temperature value PT, and the first thickness ED of the internal defect layer measured from the hot-rolled steel plate, etc. The first thickness ED of the internal defect layer may be a measured value after actually measuring the thickness of the internal defect layer of the hot-rolled steel plate.

[0106] The third module M3 may receive the composition ING of the hot-rolled steel plate, the oxygen partial pressure OPP around the hot-rolled steel plate, and the second temperature value PT of the hot-rolled steel plate from the third learning model LM3 as input data. The third module M3 may calculate the second thickness PD of the internal defect layer. The second thickness ED may be the thickness of the internal defect layer that may exist in the hot-rolled steel plate calculated by the third module M3 using at least one of the composition ING of the hot-rolled steel plate, the oxygen partial pressure OPP around the hot-rolled steel plate, and the second temperature value PT. The second thickness PD of the internal defect layer output by the third module M3 may be transmitted to the third learning model LM3.

[0107] The third learning model LM3 can compare the first thickness ED and the second thickness PD of the internal defect layer and make the third module M3 learn. As an example, when the first thickness ED and the second thickness PD of the internal defect layer are inconsistent or the difference between the two is greater than a specified value, the third learning model LM3 can adjust the weighted value and coefficient of the third calculation of the second thickness PD of the internal defect layer in the third module M3. The third learning model LM3 can make the third module M3 learn so that the measured value of the internal defect layer, i.e., the first thickness ED, and the calculated value, i.e., the second thickness PD, are consistent or the difference between the two is less than a specified value.

[0108] The fourth learning model LM4 may receive the conveying speed PV of the hot rolled steel sheet, the characteristic AC of the etching solution used in the etching process, and the first thickness EPA of the internal defect layer removed by the etching device. The characteristic AC of the etching solution may include the concentration of the etching solution in contact with the hot rolled steel sheet, the temperature of the etching solution, the composition of the etching solution, and whether an accelerator is used. The conveying speed PV of the hot rolled steel sheet may mean the speed at which the hot rolled steel sheet moves during the contact between the hot rolled steel sheet and the etching solution. The first thickness EPA of the internal defect layer may mean the thickness of the internal defect layer actually removed in the etching process performed by the conveying speed PV of the hot rolled coil and the characteristic AC of the etching solution.

[0109] The fourth module M4 may receive the conveying speed PV of the hot-rolled steel sheet and the characteristic AC of the etching solution from the fourth learning model LM4. The fourth module M4 may calculate the second thickness PPA1 of the internal defect layer that is expected to be removed by the etching device using at least one of the conveying speed PV of the hot-rolled steel sheet and the characteristic AC of the etching solution. In one embodiment, the fourth module M4 may receive the etching time determined according to the conveying speed PV and the characteristic AC of the etching solution as input values, and perform calculation of the second thickness PPA1 of the internal defect layer using the input values. The fourth module M4 may output the second thickness PPA1 of the internal defect layer to the fourth learning model LM4.

[0110] The fourth learning model LM4 can compare the second thickness PPA1 of the internal defect layer with the first thickness EPA of the internal defect layer, and make the fourth module M4 learn. For example, when the first thickness EPA of the internal defect layer and the second thickness PPA1 of the internal defect layer are inconsistent or the difference between the two is greater than a specified value, the fourth learning model LM4 can adjust the weighted value and coefficient of the fourth calculation of the second thickness PPA1 of the internal defect layer in the fourth module M4.

[0111] The fifth module M5 can generate control data for controlling the etching device. As an example, the fifth module M5 can repeatedly call the fourth module M4 to find the best control data by using an optimization method (e.g., golden section method, etc.). The fifth module M5 can select an optimization method for finding the best control data or modify the optimization method.

[0112] Figure 6 It is a diagram for explaining a learning model included in a process control system according to an embodiment of the present invention.

[0113] Reference Figure 6 When the learning model uses reinforcement learning to make each module learn, the learning model can be implemented by a deep neural network (DNN) or the like. The learning model may include an input layer IL, a hidden layer HL, and an output layer OL. As an example, a plurality of nodes included in the input layer IL, the hidden layer HL, and the output layer OL may be connected to each other in a fully connected manner. The input layer IL may include a plurality of input nodes x1-xi, and the number of the input nodes x1-xi may correspond to the number of input data. The output layer OL may include a plurality of output nodes y1-yj, and the number of the output nodes y1-yj may correspond to the number of output data.

[0114] The hidden layer HL may include first to third hidden layers HL1 - HL3 , and the number of hidden layers HL1 - HL3 may be varied. As an example, the learning model 120 may learn by adjusting the weight value of each hidden node included in the hidden layer HL.

[0115] Figure 7 It is a diagram for explaining an operating method of a process control system according to an embodiment of the present invention.

[0116] Reference Figure 7 The process control system 200 of one embodiment of the present invention may include computing modules 210 to 230. As an example, the process control system may be connected to an external system via a network, and the external system directly controls an etching device for removing at least a portion of an internal defect layer of a hot-rolled steel plate.

[0117] In one embodiment, the calculation modules 210 to 230 may calculate the thickness of the internal defect layer contained in the hot-rolled steel sheet. In one embodiment, in order to calculate the thickness of the internal defect layer, the cooling rate of the hot-rolled steel sheet along the length direction of the hot-rolled steel sheet may be required. When the phase change is not completed before the hot-rolled steel sheet is coiled, heat generation due to the phase change may occur after coiling. Therefore, the phase fraction before the hot-rolled steel sheet is coiled may be considered to calculate the temperature change of the hot-rolled steel sheet after coiling.

[0118] In one embodiment, the first module 210 may calculate the phase fraction PPF under different cooling times using the first process condition CD1. The first process condition CD1 may include the cooling rate of the hot-rolled steel sheet, the temperature of the hot-rolled steel sheet, and the composition of the hot-rolled steel sheet.

[0119] The hot rolled steel sheet may undergo a phase transformation from austenite to pearlite during the cooling process, and may generate phase transformation heat in which the temperature rises due to the phase transformation. Hot rolled high carbon steel may not complete the phase transformation during cooling due to the slower pearlite phase transformation, and further phase transformation may occur on the hot rolled steel sheet after coiling. As a result, the hot rolled steel sheet may be exposed to a high temperature oxidizing atmosphere for a long time after being coiled, and the thickness of the internal defect layer may increase.

[0120] The second module 220 can calculate the temperature PT at different elapsed times after coiling the hot rolled steel sheet using the second process condition CD2 and the environmental condition FV. As an example, the second module 220 can calculate the temperature PT in each region in the length direction of the hot rolled steel sheet. The second process condition CD2 can include the time point at which the temperature of the hot rolled steel sheet after coiling is measured and the composition of the hot rolled steel sheet.

[0121] In order to calculate the temperature of the hot-rolled steel sheet after coiling, the phase change heat generation described above needs to be considered, so the second module 220 can receive the phase fraction PPF from the first module 210. Based on the phase fraction PPF, the phase fraction at the coiling time point can be known, and the amount of phase further generated on the hot-rolled steel sheet after coiling can be known. Therefore, the second module 220 can consider the amount of phase further generated on the hot-rolled steel sheet after coiling, and calculate the temperature PT of the hot-rolled steel sheet according to the time after the hot-rolled steel sheet is coiled. Figure 7 In one embodiment shown in , time point t1 may represent a temperature reflecting the phase change heat generated by the phase change.

[0122] The third module 230 may calculate the thickness PD of the internal defect layer included in the hot-rolled steel sheet using the composition ING of the hot-rolled steel sheet and the oxygen partial pressure OPP around the hot-rolled steel sheet, etc. In one embodiment, the third module 230 may receive the temperature PT according to the elapsed time after coiling in each region of the hot-rolled steel sheet from the second module 220, and calculate the thickness PD of the internal defect layer in each of the regions of the hot-rolled steel sheet.

[0123] Figure 8 It is a flowchart for explaining an operating method of a process control system according to an embodiment of the present invention.

[0124] Reference Figure 8 , the process control system may transmit at least a portion of the calculation module to an external system (S110). As an example, the subject that transmits at least a portion of the calculation module to the external system may be a system for producing hot-rolled steel sheets and coiling the hot-rolled steel sheets in the form of hot-rolled coils. In addition, the external system that receives at least a portion of the calculation module may be a system for receiving hot-rolled coils and performing an etching process.

[0125] The external system may perform an etching process using the calculation module received in step S110. As an example, the calculation module transmitted to the external system in step S110 may be a module for generating control data for controlling the etching process. The process control system may receive the thickness of the remaining internal defect layer contained in the pickled steel plate after the etching process is completed and the control data measured in the etching device during the etching process from the external system (S120). As an example, the control data received in step S120 may be a value actually measured in the etching device, and therefore may be different from the value input to the etching device by the external system for controlling the etching device.

[0126] The process control system may calculate the thickness of the internal defect layer that is expected to be removed by the etching device using the control data received in step S120 (S130). In addition, the process control system may compare the thickness of the internal defect layer calculated in step S130 with the thickness of the remaining internal defect layer received in step S120, and cause the calculation module to learn based on the comparison result (S140). The process control system may include a learning model required in the learning of the calculation module, and the learning model may adjust the weighting values ​​and coefficients used in the calculation of at least one calculation module.

[0127] After completing the learning, the process control system may transmit at least one of the calculation modules to the external system (S150). The external system may update the stored calculation modules in an overwriting manner, etc., using the calculation modules received from the process control system. Therefore, the external system can perform the etching process in an optimized manner taking into account the thickness distribution of the internal defect layer contained in the hot-rolled steel plate.

[0128] Fig. 9 It is a block diagram simply showing a process control system according to an embodiment of the present invention.

[0129] Reference Fig. 9 The process control system 50 may include a second server 51 and an etching device 55, etc. The second server 51 may control and manage the etching device 55. The etching device 55 may receive the hot rolled coil produced by the hot rolled steel plate production device 45, and after releasing the hot rolled coil in the coiled state in the form of hot rolled steel plates, perform an etching process on the hot rolled steel plates to produce pickled steel plates.

[0130] The etching device 55 may be at least one of an acid cleaning device, a dry etching device, and a wet etching device. When the etching device 55 is an acid cleaning device, the internal defect layer may be removed by immersing the hot-rolled steel plate in an acidic etching solution. Alternatively, the internal defect layer may be removed by spraying the etching solution onto the surface of the hot-rolled steel plate, or by brushing the surface of the hot-rolled steel plate with a brush dipped in the etching solution.

[0131] The second server 51 may include a communication unit 52, a storage device 53, a processor 54, etc. The communication unit 52 may connect the second server 51 to the network so that communication is possible. For example, the second server 51 and the first server 41 may communicate via the communication unit 52. Figure 4 In the following description, the first server 41 may be a server for controlling the hot rolled steel plate production device 45. The storage device 53 may store data required for the operation of the second server 51 and the control of the etching device 55. The processor 54 may control the communication unit 52, the storage device 53, the etching device 55, and the like.

[0132] In one embodiment, the storage device 53 may store control data required to control the etching device 55. As an example, the control data stored in the storage device 53 may be data obtained by the processor 54 executing a calculation module stored in the storage device 53 or data received from an external system connected through the communication unit 52. As an example, when the control data is stored in the storage device 53 without the calculation module, the control data may be transmitted from an external system for managing the production of hot-rolled steel sheets.

[0133] The storage device 53 may include a calculation module for generating control data. The calculation module may perform calculations for controlling the etching process performed in the etching device 55. As an example, the calculation module may generate control data by considering the thickness distribution of the internal defect layer contained in the hot-rolled steel plate, and the control data can control the etching device 55 to efficiently remove the internal defect layer. In one embodiment, the calculation module stored in the storage device 53 may be a calculation module received and stored from an external system through the communication unit 52, and the external system may be a system for controlling a hot-rolled steel plate production device. However, the external system is not necessarily limited to a system for controlling a hot-rolled steel plate production device, and the calculation module may be received from a variety of external systems according to the embodiment.

[0134] As an example, the calculation module may generate control data using the thickness information of the internal defect layer received by the second server 51 through the communication unit 52. The processor 54 may input the thickness information of the internal defect layer to the calculation module stored in the storage device 53, and execute the calculation module to obtain the control data. The thickness information of the internal defect layer may include the thickness distribution of the internal defect layer along the length direction of the hot-rolled steel plate.

[0135] According to an embodiment, the calculation module stored in the storage device 53 may also generate control data using the information of the hot-rolled steel sheet received through the communication unit 52. At this time, the calculation module may calculate the thickness information of the internal defect layer contained in the hot-rolled steel sheet using the phase fraction of the hot-rolled steel sheet, the temperature of the hot-rolled steel sheet, and the composition of the hot-rolled steel sheet. In addition, the calculation module may generate control data using the thickness information of the internal defect layer. As an example, the calculation module stored in the storage device 53 may include a thickness information generation module for calculating thickness information and a control data generation module for generating control data.

[0136] The control data may include at least one of the conveying speed of the hot-rolled steel sheet conveyed by the etching device 55, the concentration of the etching solution in contact with the hot-rolled steel sheet in the etching device 55, the temperature of the etching solution, the composition of the etching solution, and whether an accelerator is used. As an example, in the thickness information of the internal defect layer, the thickness of the internal defect layer displayed in the first area and the second area of ​​the hot-rolled steel sheet may be different from each other. In this case, the first area and the second area may be areas defined at different positions along the length direction of the hot-rolled steel sheet.

[0137] In the control data, a first conveying speed of the hot-rolled steel sheet during a period in which the first region is in contact with the etching solution while passing through the etching device 55 may be different from a second conveying speed of the hot-rolled steel sheet during a period in which the second region is in contact with the etching solution while passing through the etching device 55. As an example, when the thickness of the internal defect layer in the first region is less than the thickness of the internal defect layer in the second region, the first conveying speed may be faster than the second conveying speed.

[0138] The calculation module for generating control data may determine the conveying speed of the hot rolled steel plate according to the thickness of the internal defect layer. In one embodiment, the calculation module may perform a prescribed calculation using the thickness of the internal defect layer to determine the conveying speed of the hot rolled steel plate. In addition, in one embodiment, the calculation module may also compare the prescribed reference thickness with the thickness of the internal defect layer, and determine the conveying speed of the hot rolled steel plate according to the comparison result.

[0139] In one embodiment, the second server 51 can obtain information required for updating the calculation module from the etching device 55, and feed back the information obtained from the etching device 55 to the external system through the communication unit 52. Here, the external system can be a system for storing and managing the calculation module and including a learning model for updating the calculation module. When the storage device 53 includes a learning model for updating the calculation module, the update operation of the calculation module using the information obtained from the etching device 55 can also be performed in the second server 51.

[0140] As an example, the external system may be a system for controlling the production process of hot-rolled steel sheets. The external system may update at least a portion of the calculation modules stored in the external system using information fed back from the second server 51. As an example, weights and coefficients used by at least a portion of the calculation modules stored in the external system for calculation may be adjusted.

[0141] Furthermore, the external system may transmit at least one of the updated calculation modules, such as the calculation module for generating control data, to the second server 51. The second server 51 may use the new calculation module received from the external system to update the existing calculation module stored in the storage device 53. As an example, the second server 51 may update the calculation module by overwriting the existing calculation module with the new calculation module. Therefore, the etching process may be performed using the calculation module optimized according to various conditions of the etching device 55 and / or the object of the etching process, i.e., the hot-rolled steel sheet, thereby improving the efficiency and productivity of the etching process.

[0142] In another embodiment, the second server 51 may obtain information required for updating the calculation module from the etching device 55, and directly update the calculation module stored in the storage device 53 using the information obtained from the etching device 55. In addition, as an example, the storage device 53 may also store only control data for controlling the etching device 55 in the absence of an additional calculation module. In this case, the second server 51 may feed back the information required for updating the calculation module obtained from the etching device 55 to the external system, and receive the new control data generated by the updated calculation module in the external system and store it in the storage device 53.

[0143] Fig.10 It is a diagram for explaining an operating method of a process control system according to an embodiment of the present invention.

[0144] Reference Fig.10 , the process control system 300 may include calculation modules 310 and 320. As an example, the calculation modules 310 and 320 may be modules stored in the process control system 300 for controlling the etching device for execution. In addition, the calculation modules 310 and 320 may also be stored in an external system connected to the process control system 300 through a network.

[0145] The calculation modules 310 and 320 may be transmitted and stored in the process control system 300 in a state after learning by the learning model of the external system. In one embodiment, the calculation modules 310 and 320 stored in the process control system 300 for controlling the etching device may be modules received from the external system. Figure 5 An embodiment shown in FIG. 1 is taken as an example to illustrate as follows: Figure 5 In the calculation module 110 represented in FIG. 1 , the control data generation module 112 may be transmitted and stored in the process control system 300 as calculation modules 310 and 320 .

[0146] The process control system 300 may determine control data for controlling the etching device. The process control system 300 may receive thickness information PD of the internal defect layer. Fig. 9Similarly to the illustrated embodiment, the thickness information PD of the internal defect layer received by the process control system 300 may be the thickness of the internal defect layer calculated to be possibly contained in the hot-rolled steel plate, and may include the thickness distribution of the internal defect layer in different regions of the hot-rolled steel plate. The process control system 300 may calculate the control data PPV2 based on the thickness information PD of the internal defect layer.

[0147] In one embodiment, the calculation modules 310 and 320 may include a first module 310 and a second module 320, etc. The second module 320 may receive thickness information PD of the internal defect layer. The thickness information PD of the internal defect layer may be the thickness of the internal defect layer expected to exist in the hot-rolled steel plate, and the thickness information PD may also be inconsistent with the thickness of the internal defect layer actually existing in the hot-rolled steel plate. In addition, the second module 320 may receive a thickness target value GD of the remaining internal defect layer. The remaining internal defect layer may be an internal defect layer existing in the pickled steel plate after the etching process is completed. As an example, when the internal defect layer is to be completely removed by an etching process, the thickness target value GD of the remaining internal defect layer may be 0. According to an embodiment, the thickness target value GD of the remaining internal defect layer may also be greater than 0. The second module 320 may periodically call the first module 310 to calculate the optimal control data PPV2.

[0148] The second module 320 may output the initial value of the control data to the first module 310. The initial value of the control data may include the characteristic AC of the etching solution measured from the tank containing the etching solution in the etching device and the conveying speed PPV1 of the hot-rolled steel sheet, etc. The initial value of the control data may be determined as an arbitrary value, or may be determined by a value measured in real time from the etching device. When the initial value of the control data is determined as an arbitrary value, the initial value of the control data may be determined by an external system running the hot-rolled steel sheet production device or a process control system running the etching device. The first module 310 may calculate the thickness PPA2 of the internal defect layer expected to be removed by the etching device using at least one of the characteristic AC of the etching solution and the conveying speed PPV1.

[0149] The second module 320 may receive the thickness PPA2 of the internal defect layer from the first module 310. The second module 320 may determine whether the characteristic AC of the etching solution and the arbitrarily set delivery speed PPV1 are consistent with the optimal control data PPV2 based on the thickness PPA2 of the internal defect layer. As an example, the second module 320 may compare the difference between the thickness information PD of the internal defect layer and the target thickness value GD of the remaining internal defect layer with the thickness PPA2 of the internal defect layer calculated by the first module 310. When the comparison result shows that the two are inconsistent, the second module 320 may adjust at least one of the characteristic AC of the etching solution and the delivery speed PPV1 and input it to the first module 310. In the manner described above, the second module 320 may change at least one of the characteristic AC of the etching solution and the delivery speed PPV1 and call the first module 310 until the difference between the thickness information PD of the internal defect layer and the target thickness value GD of the remaining internal defect layer is consistent with the thickness PPA2 of the internal defect layer calculated by the first module 310, or the difference between the two reaches a specified value or less.

[0150] [Table 1] is a table for explaining a method of generating the optimal control data PPV2 by the second module 320. For ease of explanation, it is assumed in [Table 1] that the characteristics AC of the etching solutions are the same. The second module 320 may calculate a target removal thickness GPA indicating how much of the internal defect layer should be removed based on the difference between the thickness information PD of the internal defect layer expected to exist in the hot-rolled steel sheet and the target thickness value GD of the remaining internal defect layer.

[0151] The X region, Y region, and Z region defined in [Table 1] may be regions defined at different positions in the length direction of the hot-rolled steel sheet. As an example, the X region and the Z region may be closer to the end of the hot-rolled steel sheet in the length direction than the Y region. In other words, the Y region may be arranged between the X region and the Z region in the length direction. Referring to [Table 1], in the first region, the target removal thickness GPA may be determined as the difference between the thickness information PD calculated as the internal defect layer existing in the hot-rolled steel sheet and the target thickness value GD of the remaining internal defect layer, 1 μm (=3 μm-2 μm).

[0152] Referring to [Table 1], the thickness PPA2 of the internal defect layer expected to be removed by the etching device may be 2 μm when the delivery speed PPV1 of the first module 310 is 15 mpm. The thickness PPA2 of the internal defect layer expected to be removed by the etching device is greater than the target removal thickness GPA, so the second module 320 may increase the delivery speed PPV1 to 20 mpm, which is faster than 15 mpm, and transmit it to the first module 310. When the delivery speed PPV1 is 20 mpm, and the thickness PPA2 of the internal defect layer expected to be removed by the etching device calculated by the first module 310 is not equal to 1 μm, the second module 320 may change the delivery speed PPV1 back to a value different from 20 mpm and output the value to the first module 310. On the contrary, when the conveying speed PPV1 is 20 mpm and the thickness PPA2 of the internal defect layer calculated by the first module 310 is 1 μm, the thickness PPA2 of the internal defect layer removed by the etching device is expected to be consistent with the target removal thickness GPA, so the second module 320 can determine the optimal conveying speed for the X region of the hot-rolled steel plate as 20 mpm.

[0153] [Table 1]

[0154] project X Zone Y area Z Zone PD 3μm 10μm 3μm GD 2μm 2μm 2μm GPA 1μm 8μm 1μm PPV1 15mpm 10mpm 15mpm PPA2 2μm 4μm 2μm PPV2 20mpm 5mpm 20mpm

[0155] mpm = meter per minute

[0156] exist Fig.10 In the embodiment shown, the control data generated by the computing modules 310 and 320 of the process control system 300 is used as an example for explanation, but it is not necessarily limited to this form. According to the embodiment, the control data can also be generated by the computing module of the external system connected to the process control system 300 through the network. In this case, the process control system 300 can receive the control data generated by the external system through the network, and control the etching device using the received control data.

[0157] Therefore, the process control system 300 may generate control data including the conveying speed of the hot-rolled steel plate based on the thickness information PD of the internal defect layer. As an example, as described above, the thickness of the internal defect layer of the hot-rolled steel plate may be different according to a plurality of regions defined along the length direction. As an example, the thickness of the internal defect layer included in the region that is cooled in a state exposed to the outside may be smaller than the thickness of the internal defect layer included in the region that is not exposed to the outside and is cooled slowly.

[0158] As an example, the hot rolled steel sheet may be sufficiently exposed to the etching solution regardless of the region of the hot rolled steel sheet to perform the etching process so as to sufficiently remove the internal defect layer contained in the hot rolled steel sheet. However, the above method may increase the time of the etching process and / or the etching solution input in the etching process, and thus may reduce productivity.

[0159] According to one embodiment of the present invention, the thickness of the internal defect layer can be calculated along the length direction of the hot-rolled steel plate, and based on the calculated thickness information of the internal defect layer, the control data that can control the etching process with the best efficiency can be calculated. Therefore, the time of the etching process can be shortened and the amount of etching solution used can be reduced, thereby improving productivity. In addition, the thickness deviation of the internal defect layer generated along the length direction and the like on the pickled steel plate after the etching process is completed can be reduced.

[0160] As an example, in the length direction of the hot-rolled steel plate, the region where the thickness of the internal defect layer is less than the preset reference thickness t can be defined as the first region, and the region where the thickness of the internal defect layer is greater than the reference thickness t can be defined as the second region. At this time, the conveying speed of the hot-rolled steel plate during the period when the first region is in contact with the etching solution can be faster than the conveying speed of the hot-rolled steel plate during the period when the second region is in contact with the etching solution. Alternatively, the conveying speeds for the first region and the second region can be determined by receiving the thickness information of the internal defect layer and determining the calculation of the conveying speed without separately setting the reference thickness t.

[0161] As a result, the second region can be in contact with the etching solution for a longer time than the first region. Therefore, it is possible to minimize the thickness deviation of the remaining internal defect layer included in the pickled steel plate after the etching process is completed.

[0162] According to an embodiment, a plurality of reference thicknesses t may be set. As an example, when there are two reference thicknesses t1 and t2, the hot-rolled steel sheet may be divided into at least three regions according to the thickness of the internal defect layer. In other words, when the number of reference thicknesses is n, the hot-rolled steel sheet may be divided into n+1 regions. When the size of the reference thickness is defined as shown in Mathematical Formula 1, the conveying speed of the hot-rolled steel sheet during the period when each of the n+1 regions included in the hot-rolled steel sheet is in contact with the etching solution may be defined as shown in Mathematical Formula 2.

[0163] [Mathematical formula 1]

[0164] t1<t2<t3<…<tn

[0165] [Mathematical formula 2]

[0166] The conveying speed of the first area>the conveying speed of the second area>…>the conveying speed of the (n+1)th area

[0167] According to the embodiment, the etching rate can be adjusted in addition to the conveying speed of the hot-rolled steel sheet. For example, the area with a relatively small thickness of the internal defect layer can be brought into contact with an etching solution with a relatively small etching rate, and the area with a relatively large thickness of the internal defect layer can be brought into contact with an etching solution with a relatively high etching rate. Alternatively, the etching rate can also be adjusted by changing the area of ​​the brush stained with the etching solution or the pressure of the brush.

[0168] Fig.11 It is a diagram for explaining a learning method of a calculation module included in a process control system according to an embodiment of the present invention. Fig.12 It is a diagram for explaining an etching process according to an embodiment of the present invention. Fig.13 The diagram is provided to illustrate an etching process according to an embodiment of the present invention.

[0169] First, refer to Fig.12 , the etching device 500 can be based on the previously described Fig.10 The control data PPV2 determined in the embodiment described above is used to perform an etching process, thereby removing at least a portion of the internal defect layer of the hot-rolled steel sheet 510. Fig.12 During the etching process performed by the etching device 500, the measuring instruments MI1 and MI2 can measure the thickness ERD of the remaining internal defect layer in at least a portion of the pickled steel plate 520 after the etching process is completed, and collect control data EPV in the tank TK or the like that performs the etching process. As an example, the thickness ERD of the remaining internal defect layer can be measured in multiple areas, so the position information PI can be collected together. The control data EPV collected by the first measuring instrument MI1 is the control data EPV actually measured in the etching device 500 including the tank TK. Due to mechanical errors, signal delays, process errors, etc., the value of the control data EPV may be different from the value of the control data PPV2 input to the etching device 500. The first measuring instrument MI1 can obtain at least one of the conveying speed of the hot-rolled steel plate 510 and the characteristics of the etching solution in contact with the hot-rolled steel plate 510 in the tank TK.

[0170] Reference Fig.12 , the etching device 500 may include a coiler CL, an uncoiler UCL, a tank TK, a first measuring instrument MI1, a second measuring instrument MI2, and the like. The uncoiler UCL allows a hot-rolled steel plate 510 in the form of a strip steel formed by unwinding a hot-rolled coil HC to enter the tank TK. The hot-rolled steel plate 510 may be etched while passing through an etching solution contained in the tank TK. Alternatively, the hot-rolled steel plate 510 may be etched by an etching solution sprayed around the hot-rolled steel plate 510 and / or a brush dipped in the etching solution, etc. while the hot-rolled steel plate 510 passes through the tank TK.

[0171] During the etching process, the etching device 500 can be controlled according to the control data PPV2. As an example, the conveying speed of the hot-rolled steel plate 510 can be different in each area in the length direction of the hot-rolled steel plate 510 according to the control data PPV2. During the etching process performed by the etching device 500, the first measuring instrument MI1 connected to the tank TK can measure the control data EPV at at least one measurement time point. As described above, due to mechanical errors and operation delays, at least a part of the control data PPV2 input to the etching device 500 and the control data EPV measured by the first measuring instrument MI1 from the etching device 500 may have different values ​​from each other. The first measuring instrument MI1 can transmit the measured control data EPV to the external system 400.

[0172] Reference Fig.11 The external system 400 may be a system for managing the calculation modules 411 to 415 (410), and may include a learning model LMT for updating the calculation module 410 through learning. As an example, the external system 400 may update the calculation module 410 using information collected by the first measuring instrument MI1 and the second measuring instrument MI2 in the etching device 500. The external system 400 may control the etching device 500 through the control data generated by the updated calculation module 410, thereby operating the etching device 500 in an optimal state.

[0173] exist Fig.13 In the illustrated embodiment, the horizontal axis represents the position in the length direction of the hot-rolled steel plate, and the vertical axis represents the thickness PD of the internal defect layer and the conveying speed. As an example, the thickness PD information of the internal defect layer may be a thickness value of the internal defect layer that may exist in the hot-rolled steel plate calculated by at least a part of the calculation module 410 included in the external system 400.

[0174] Reference Fig.13 , the thickness PD of the internal defect layer may be calculated to be greater in the Y region than in the X region and the Z region. Similar to the description made above with reference to Table 1, the X region, the Y region, and the Z region may be regions that appear in sequence along the length direction, and the X region and the Z region may be regions that are closer to the end of the hot-rolled steel sheet than the Y region in the length direction. The Y region may be a region between the X region and the Z region.

[0175] In one embodiment, the calculation module 410 of the external system 400 may calculate the conveying speed OPV for the hot-rolled steel sheet according to the thickness PD of the internal defect layer. The conveying speed OPV may be the speed at which the hot-rolled steel sheet 510 is actually conveyed in the etching device 500 when the etching process is performed according to the control data PPV2 input to the etching device 500. Since the thickness of the internal defect layer may be calculated to be greater in the Y region than in the X region and the Z region, the conveying speed OPV may be relatively slow during the period when the Y region is in contact with the etching solution so as to be able to sufficiently remove the internal defect layer in the Y region.

[0176] The actual transport speed EPV may be a value actually measured in the etching device 500 that performs the etching process based on the transport speed OPV. The actual transport speed EPV may reflect errors and operation delays of the etching device 500, and therefore, the actual transport speed EPV may be different from the transport speed OPV set by the control data PPV2.

[0177] As an example, in order to completely remove the internal defect layer, the thickness of the internal defect layer present in the second region D2 can be used as a reference, and the conveying speed TPV can be uniformly maintained and the etching process can be performed. However, at this time, the productivity may be reduced due to the slowdown of the etching process. On the contrary, according to one embodiment of the present invention, the conveying speed OPV calculated differently for each region of the hot-rolled steel plate can be applied to perform the etching process. Therefore, not only can the internal defect layer be effectively removed, but also the time of the etching process and the amount of etching solution put into the etching process can be reduced. Therefore, the productivity of the etching process can be improved.

[0178] Refer again Fig.12 Before the etching device 500 uses the coiler CL to coil the pickled steel plate 520 after etching to prepare the pickled steel coil PC, the second measuring instrument MI2 can measure the position information PI of the pickled steel plate 520 and the thickness ERD of the remaining internal defect layer at the position corresponding to the position information PI.

[0179] According to an embodiment, at least one measurement position may be designated on the pickled steel plate 520 after the etching process is completed, and a portion of the pickled steel plate 520 may be cut at the measurement position for sampling. The cross section of the sample taken out from the pickled steel plate 520 may be observed through a microscope to measure the thickness of the remaining internal defect layer. The measurement position is equivalent to the position information PI of the pickled steel plate 520, and the thickness of the remaining internal defect layer is equivalent to the thickness ERD of the remaining internal defect layer at the position corresponding to the position information PI.

[0180] Refer again Fig.11The learning model 420 may receive the thickness ERD of the remaining internal defect layer measured by the second measuring instrument MI2 of the etching device 500 at at least one measuring position of the pickled steel plate 520. The fifth module 415 may receive the control data EPV measured from the etching device 500 during the etching process. As an example, the fifth module 415 may receive the control data EPV measured from the process control system including the etching device 500 through the network.

[0181] The fifth module 415 may output the measured control data EPV to the fourth module 414. The fourth module 414 may calculate the thickness PPA2 of the internal defect layer expected to be removed by the etching device 500 based on the measured control data EPV. The fifth module 415 may receive the thickness PPA2 of the internal defect layer from the fourth module 414. The fifth module 415 may calculate the expected thickness PRD of the remaining internal defect layer based on the thickness PPA2 of the internal defect layer expected to be removed by the etching device 500. The expected thickness PRD of the remaining internal defect layer may be the thickness of the internal defect layer expected to remain in the pickled steel plate 520 after the etching process is performed according to the measured control data EPV.

[0182] The learning model LMT may receive the estimated thickness PRD of the internal defect layer from the fifth module 415. The learning model LMT may compare the thickness ERD of the remaining internal defect layer actually measured from the pickled steel plate 520 with the estimated thickness PRD of the remaining internal defect layer. The learning model LMT may enable at least one of the calculation modules 411 to 415 to learn so that the thickness ERD of the remaining internal defect layer measured from the pickled steel plate 520 and the estimated thickness PRD of the remaining internal defect layer are consistent or the difference between the two is less than a specified value. For example, the learning model LMT may also enable all the calculation modules 411 to 415 to learn simultaneously, or may selectively enable only a specific model to learn.

[0183] According to an embodiment, it is also possible to configure a system including a server and an etching device. Fig. 9 The process control system 50 includes a learning model. Fig. 9 The learning model in the process control system 50 can include Fig. 9 The calculation module in the process control system 50 is learned. Fig.14 and Fig.15 For Fig. 9 The learning model in the process control system 50 includes Fig. 9 A method for learning the calculation module in the process control system 50 is described.

[0184] Fig.14 It is a diagram for explaining an initial learning method of a calculation module included in a process control system according to an embodiment of the present invention.

[0185] Reference Fig.14 , the process control system 600 may include a calculation module 610 and a learning model 620, and the calculation module 610 and the learning model 620 may be stored in a storage device. As an example, the calculation module 610 may be a control data generation module. The learning model 620 may include a first learning model LM1 and a feedback learning model LMT. The first learning model LM1 may be a model for initial learning of the first module M1, and the feedback learning model LMT may be a model for learning at least one of the first module M1 and the second module M2 after the etching process is completed. In one embodiment, the feedback learning model LMT may also enable the first module M1 and the second module M2 to learn at the same time. In addition, according to the embodiment, it is also possible not to distinguish between the first learning model LM1 and the feedback learning model LMT, and one learning model may perform the learning of both the first module M1 and the second module M2.

[0186] The first learning model LM1 may receive the conveying speed PV of the hot rolled steel sheet, the characteristic AC of the etching solution used in the etching process, and the first thickness EPA of the internal defect layer removed by the etching device. The characteristic AC of the etching solution may include the concentration of the etching solution in contact with the hot rolled steel sheet, the temperature of the etching solution, the composition of the etching solution, and whether an accelerator is used. The conveying speed PV of the hot rolled steel sheet may mean the speed at which the hot rolled steel sheet moves during the contact between the hot rolled steel sheet and the etching solution. The first thickness EPA of the internal defect layer may mean the thickness of the internal defect layer actually removed in the etching process performed by the conveying speed PV of the hot rolled coil and the characteristic AC of the etching solution.

[0187] The first module M1 may receive the conveying speed PV of the hot-rolled steel sheet and the characteristic AC of the etching solution from the first learning model LM1. The first module M1 may calculate the second thickness PPA1 of the internal defect layer expected to be removed by the etching device using at least one of the conveying speed PV of the hot-rolled steel sheet and the characteristic AC of the etching solution. In one embodiment, the first module M1 may receive the etching time determined according to the conveying speed PV and the characteristic AC of the etching solution as input values, and use the input values ​​to perform a calculation for calculating the second thickness PPA1 of the internal defect layer. The first module M1 outputs the second thickness PPA1 of the internal defect layer to the first learning model LM1.

[0188] The first learning model LM1 can compare the second thickness PPA1 of the internal defect layer with the first thickness EPA of the internal defect layer, and make the first module M1 learn. For example, when the first thickness EPA of the internal defect layer and the second thickness PPA1 of the internal defect layer are inconsistent or the difference between the two is greater than a specified value, the first learning model LM1 can adjust the weighted value and coefficient of the first calculation used in the first module M1 to calculate the second thickness PPA1 of the internal defect layer.

[0189] The second module M2 can generate control data for controlling the etching device. As an example, the second module M2 can repeatedly call the first module M1 to find the best control data by using an optimization method (e.g., golden section method, etc.). The second module M2 can select an optimization method for finding the best control data or modify the optimization method.

[0190] Fig.15 It is a diagram for explaining a learning method of a calculation module included in a process control system according to an embodiment of the present invention.

[0191] Reference Fig.15 The process control system 700 may be a system for managing the computing modules 711 and 712 (710), and may include a learning model LMT for enabling the computing module 710 to learn. As an example, the process control system 700 may enable the computing module 710 to learn using information collected by the first measuring instrument M11 and the second measuring instrument MI2 in the etching device 500. The etching device 500 may be controlled by control data generated by the computing module 710 after learning, so that the etching device 500 may be operated in an optimal state.

[0192] The learning model 720 may receive the thickness ERD of the remaining internal defect layer measured by the second measuring instrument M12 of the etching device 500 at at least one measuring position of the pickled steel plate 520. The second module 712 may receive the control data EPV measured from the etching device 500 during the etching process.

[0193] The second module 712 may output the measured control data EPV to the first module 711. The first module 711 may calculate the thickness PPA2 of the internal defect layer expected to be removed by the etching device 500 based on the measured control data EPV. The second module 712 may receive the thickness PPA2 of the internal defect layer from the first module 711. The second module 712 may calculate the expected thickness PRD of the remaining internal defect layer based on the thickness PPA2 of the internal defect layer expected to be removed by the etching device 500. The expected thickness PRD of the remaining internal defect layer may be the thickness of the internal defect layer expected to remain in the pickled steel plate 520 after the etching process is performed according to the measured control data EPV.

[0194] The learning model LMT may receive the estimated thickness PRD of the internal defect layer from the second module 712. The learning model LMT may compare the thickness ERD of the remaining internal defect layer actually measured from the pickled steel plate 520 with the estimated thickness PRD of the remaining internal defect layer. The learning model LMT may enable at least one of the calculation modules 711 and 712 to learn so that the thickness ERD of the remaining internal defect layer measured from the pickled steel plate 520 and the estimated thickness PRD of the remaining internal defect layer are consistent or the difference between the two is less than a specified value. For example, the learning model LMT may also enable all the calculation modules 711 and 712 to learn at the same time, or may selectively enable only a specific model to learn.

[0195] Fig.16 It is a flowchart for explaining an operating method of a process control system according to an embodiment of the present invention.

[0196] Reference Fig.16 , a process control system for controlling an etching process may receive a calculation module from an external system (S210). The calculation module received in step S210 may generate control data for controlling the etching process. The process control system may perform an etching process using the control data generated by the calculation module (S220). At least a portion of the internal defect layer contained in the hot-rolled steel plate may be removed by the etching process.

[0197] The process control system may transmit to the external system the control data actually measured in the etching device performing the etching process and the thickness of the remaining internal defect layer contained in the pickled steel plate after the etching process is completed (S230). The control data transmitted to the external system in step S230 may be the value actually measured from the etching device. The thickness of the remaining internal defect layer may be measured by taking out a local area of ​​the pickled steel plate as a sample and then inspecting it under a microscope.

[0198] The external system may use the control data received in step S230 and the thickness of the remaining internal defect layer to make the calculation module learn. After the learning is completed, the process control system may receive at least one of the calculation modules that have completed the learning from the external system (S240). The process control system may use the calculation module received in step S240 to update the existing calculation module (S150). Therefore, by reflecting the process error that may occur in the etching device, etc., the etching process can be accurately controlled.

[0199] As an example, the external system may mean a system for managing and controlling the production process of hot rolled steel sheets. This is an exemplary embodiment, and the claims are not limited thereto.

[0200] Fig.17 It is a diagram for explaining an operating method of a process control system according to an embodiment of the present invention.

[0201] Reference Fig.17 , the first system SYS1 for preparing the hot-rolled steel sheet may generate the thickness information PD of the internal defect layer (S310). The thickness information PD of the internal defect layer generated in step S310 may be the thickness of the internal defect layer calculated based on at least one of the temperature at different elapsed times after coiling measured in each region of the hot-rolled steel sheet defined in the length direction, the composition of the hot-rolled steel sheet, and the oxygen partial pressure around the hot-rolled steel sheet. The first system SYS1 may transmit the thickness information PD of the internal defect layer to the second system SYS2 via the network (S320).

[0202] The second system SYS2 can use the thickness information PD of the internal defect layer to generate control data PPV for controlling the etching process of the hot-rolled steel plate (S330). The second system SYS2 can perform an etching process to remove at least a portion of the internal defect layer of the hot-rolled steel plate according to the control data PPV (S340). The second system SYS2 can obtain position information PI representing a specific position of the hot-rolled steel plate, the thickness ERD of the remaining internal defect layer measured at a position corresponding to the position information PI, and control data EPV during the etching process (S350). The control data EPV obtained in step S350 is data actually measured from the etching device during the etching process, and may be inconsistent with the control data PPV generated in step S330 due to various factors such as process errors and signal delays. The second system SYS2 can transmit the information obtained in step S350 to the first system SYS1 (S360).

[0203] The first system SYS1 may calculate the estimated thickness PRD of the remaining internal defect layer using the information received in step S360 (S370). The first system SYS1 may compare the estimated thickness PRD of the remaining internal defect layer calculated in step S370 with the thickness ERD of the remaining internal defect layer actually measured at at least one position (S380). The first system SYS1 may learn at least one of the calculation modules included in the first system SYS1 so that the estimated thickness PRD of the remaining internal defect layer calculated at a specific position of the hot-rolled steel plate and the measured thickness ERD of the remaining internal defect layer are consistent or the difference between the two reaches a specified value or less (S390).

[0204] The first system SYS1 may transmit at least one of the learned calculation modules to the second system SYS2 (S400). The second system SYS2 may update the calculation modules pre-stored in the second system SYS2 using the calculation modules received from the first system SYS1 (S410).

[0205] The present invention is not limited to the above-mentioned embodiments and drawings, but is limited by the appended claims. Therefore, within the scope of the technical concept of the present invention recorded in the claims, those skilled in the art may perform various forms of substitution, deformation and change, which should also fall within the scope of the present invention.

Claims

1. A process control system comprising: a storage device for storing a calculation module for generating thickness information of an internal defect layer included in the carbon steel product based on at least one of a composition, a cooling rate, a phase fraction, and a temperature of the carbon steel product before an etching process is performed in a process including a hot rolling process for producing the carbon steel product; A communications unit connected to the network; and a processor, configured to transmit at least one of thickness information of the internal defect layer and control data for controlling the etching process to an external server through the communication unit, wherein the external server is configured to control the etching process for removing at least a portion of the internal defect layer; Wherein, the storage device is used to store a learning model used to enable the computing module to learn; Wherein, the calculation module comprises a first module, and the first module is used to calculate the phase fraction before coiling the carbon steel product; Wherein, the calculation module further includes a second module, and the second module is used to calculate the temperature change of the carbon steel product; Wherein, the calculation module further includes a third module, and the third module is used to calculate the thickness of the internal defect layer contained in the carbon steel product; Wherein, the calculation module further includes a fourth module, and the fourth module is used to calculate the thickness of the internal defect layer removed in the etching process based on the control data; Wherein, the calculation module further includes a fifth module, and the fifth module is used to generate the control data; The learning model includes a feedback learning model, and the feedback learning model enables at least one of the first to fifth modules to learn after the etching process is completed.

2. The process control system according to claim 1, wherein: The processor is configured to compare the phase fraction measured from the carbon steel product with the phase fraction calculated by the first module based on at least one of a temperature of the carbon steel product and a composition of the carbon steel product, and cause the first module to learn.

3. The process control system according to claim 1, wherein: The processor is used to compare the temperature change calculated by the second module using at least one of the phase fraction calculated before coiling the carbon steel product, the elapsed time after coiling the carbon steel product, and the composition of the carbon steel product with the temperature change measured from the carbon steel product, and cause the second module to learn.

4. The process control system according to claim 1, wherein: The processor is used to compare the thickness of the internal defect layer calculated by the third module using at least one of the temperature change calculated based on the elapsed time after the carbon steel product is coiled, the composition of the carbon steel product, and the oxygen partial pressure around the carbon steel product with the thickness of the internal defect layer measured from the carbon steel product, and enable the third module to learn.

5. The process control system according to claim 1, wherein: The third module is used to respectively calculate the thickness of the internal defect layer in a plurality of regions distinguished along the length direction of the carbon steel product.

6. The process control system according to claim 1, wherein: The processor is used to compare the thickness of the remaining internal defect layer contained in the pickled carbon steel product after completing the etching process with the thickness of the internal defect layer calculated by the fourth module, and enable the fourth module to learn.

7. The process control system according to claim 1, wherein: The processor is used to compare the thickness of the internal defect layer calculated by the fourth module using the control data measured by the external server from the etching device performing the etching process with the thickness of the remaining internal defect layer measured from the pickled carbon steel product after completing the etching process, and enable the calculation module to learn.

8. The process control system according to claim 1, wherein: The control data includes at least one of a conveying speed of the carbon steel product in the etching process, a concentration of an etching solution in contact with the carbon steel product in the etching process, a temperature of the etching solution, a composition of the etching solution, and whether an accelerator is used.

9. The process control system according to claim 1, wherein: The carbon steel product comprises a first region and a second region, wherein the internal defect layer has a first thickness in the first region and the internal defect layer has a second thickness different from the first thickness in the second region, The control data includes a first conveying speed for conveying the first region and a second conveying speed for conveying the second region in the etching process, the first conveying speed and the second conveying speed being different from each other.

10. The process control system according to claim 1, wherein: The etching process is at least one of an acid pickling process, a dry etching process and a wet etching process.

Images